View abdullahceylan's full-sized avatar
:octocat:
Focusing
Abdullah Musab Ceylan abdullahceylan
:octocat:
Focusing
Highlights
Lists (11)
Sort Name ascending (A-Z)
Starred repositories
Streaming Flux editor: live camera→ editing every frames at interactive FPS based on FLUX.2-Klein-4B. Runs on a single H100 at 15+ FPS
Real-time global intelligence dashboard — AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Autonomous AI development loop for Claude Code with intelligent exit detection
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
A TTS that fits in your CPU (and pocket)
VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning
Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal is...
State-of-the-art CLIP/SigLIP embedding models finetuned for the fashion domain. +57% increase in evaluation metrics vs FashionCLIP 2.0.
A powerful tool that translates ComfyUI workflows into executable Python code.
The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.
Official SeedVR2 Video Upscaler for ComfyUI
Qwen-Image text to image lora trainer
A web video player built for the HTML5 world using React library.
The ultimate training toolkit for finetuning diffusion models
A simple standalone viewer for reading prompts from Stable Diffusion generated image outside the webui.
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
A powerful node suite for ComfyUI that streamlines your workflow. It offers smart prompt management, image metadata analysis, visual comparison tools, customizable templates, history tracking, and ...